© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 41802
    Prev
    Next
    INDEX
    Explanations

    language governing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    shire
    -0.08
    åĽ¾æºIJ
    -0.08
    ness
    -0.08
    OrUpdate
    -0.07
    Åijl
    -0.07
    igli
    -0.07
    yled
    -0.07
    igny
    -0.07
    aylor
    -0.07
    çĦ¶å¤§
    -0.07
    POSITIVE LOGITS
    -speaking
    0.10
    ifest
    0.09
    agement
    0.09
    =en
    0.09
    less
    0.08
    žÃŃ
    0.08
    athering
    0.08
    xce
    0.08
    uale
    0.08
    -language
    0.08
    Activations Density 0.038%

    No Known Activations